<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Knowledge-Graph on Noureddine RAMDI</title><link>https://ramdi.fr/tags/knowledge-graph/</link><description>Recent content in Knowledge-Graph on Noureddine RAMDI</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 23 May 2026 20:41:27 +0000</lastBuildDate><atom:link href="https://ramdi.fr/tags/knowledge-graph/index.xml" rel="self" type="application/rss+xml"/><item><title>Graphify: Local AST parsing and AI-enhanced knowledge graphs for codebases</title><link>https://ramdi.fr/github-stars/graphify-local-ast-parsing-and-ai-enhanced-knowledge-graphs-for-codebases/</link><pubDate>Sat, 09 May 2026 11:42:26 +0000</pubDate><guid>https://ramdi.fr/github-stars/graphify-local-ast-parsing-and-ai-enhanced-knowledge-graphs-for-codebases/</guid><description>Graphify uses local tree-sitter parsers to build interactive codebase knowledge graphs, integrating with AI coding assistants while preserving privacy. Supports 25+ languages and multi-format assets.</description></item><item><title>HASH: Autonomous AI-driven knowledge graph platform with Rust and multi-service architecture</title><link>https://ramdi.fr/github-stars/hash-autonomous-ai-driven-knowledge-graph-platform-with-rust-and-multi-service-architecture/</link><pubDate>Tue, 05 May 2026 16:46:42 +0000</pubDate><guid>https://ramdi.fr/github-stars/hash-autonomous-ai-driven-knowledge-graph-platform-with-rust-and-multi-service-architecture/</guid><description>HASH is a Rust-based multi-tenant knowledge graph platform using autonomous AI agents to build and validate data. It combines Rust backend, TypeScript workers, and Docker services with LLM integrations.</description></item><item><title>ctx: managing AI skills and agents with a context-aware knowledge graph</title><link>https://ramdi.fr/github-stars/ctx-managing-ai-skills-and-agents-with-a-context-aware-knowledge-graph/</link><pubDate>Mon, 04 May 2026 10:23:02 +0000</pubDate><guid>https://ramdi.fr/github-stars/ctx-managing-ai-skills-and-agents-with-a-context-aware-knowledge-graph/</guid><description>ctx builds a 104K-node knowledge graph to optimize AI skill and agent selection for Claude Code, solving context window bloat with a graph-based recommender and lifecycle management.</description></item><item><title>graph-memory: a knowledge graph context engine plugin for AI agents using dual-path recall</title><link>https://ramdi.fr/github-stars/graph-memory-a-knowledge-graph-context-engine-plugin-for-ai-agents-using-dual-path-recall/</link><pubDate>Mon, 04 May 2026 10:23:02 +0000</pubDate><guid>https://ramdi.fr/github-stars/graph-memory-a-knowledge-graph-context-engine-plugin-for-ai-agents-using-dual-path-recall/</guid><description>graph-memory compresses AI agent context by 75% using a knowledge graph and dual-path recall with Personalized PageRank. It combines precise entity search and semantic matching for improved memory across sessions.</description></item><item><title>Memary: Recursive Knowledge Graph Memory for Autonomous AI Agents</title><link>https://ramdi.fr/github-stars/memary-recursive-knowledge-graph-memory-for-autonomous-ai-agents/</link><pubDate>Mon, 04 May 2026 10:23:02 +0000</pubDate><guid>https://ramdi.fr/github-stars/memary-recursive-knowledge-graph-memory-for-autonomous-ai-agents/</guid><description>Memary is an open-source memory layer for AI agents using knowledge graphs and recursive retrieval to efficiently store and query agent memories. It supports multi-agent setups and integrates with LlamaIndex and OpenAI.</description></item><item><title>AI Knowledge Graph Generator: Building structured graphs from unstructured text with LLMs</title><link>https://ramdi.fr/github-stars/ai-knowledge-graph-generator-building-structured-graphs-from-unstructured-text-with-llms/</link><pubDate>Mon, 04 May 2026 10:23:01 +0000</pubDate><guid>https://ramdi.fr/github-stars/ai-knowledge-graph-generator-building-structured-graphs-from-unstructured-text-with-llms/</guid><description>A Python tool that converts unstructured text into interactive knowledge graphs using a three-phase LLM pipeline with SPO triplet extraction, entity standardization, and relationship inference.</description></item><item><title>Automating knowledge graph extraction from text with LangChain and GPT-4o</title><link>https://ramdi.fr/github-stars/automating-knowledge-graph-extraction-from-text-with-langchain-and-gpt-4o/</link><pubDate>Mon, 04 May 2026 10:23:01 +0000</pubDate><guid>https://ramdi.fr/github-stars/automating-knowledge-graph-extraction-from-text-with-langchain-and-gpt-4o/</guid><description>This repo uses LangChain&amp;rsquo;s experimental graph transformers with GPT-4o to extract and visualize knowledge graphs from unstructured text, offering a practical LLM-based information extraction pattern.</description></item><item><title>SwarmVault: a local-first knowledge compiler with contradiction detection and hybrid search</title><link>https://ramdi.fr/github-stars/swarmvault-a-local-first-knowledge-compiler-with-contradiction-detection-and-hybrid-search/</link><pubDate>Mon, 04 May 2026 10:23:01 +0000</pubDate><guid>https://ramdi.fr/github-stars/swarmvault-a-local-first-knowledge-compiler-with-contradiction-detection-and-hybrid-search/</guid><description>SwarmVault compiles raw sources into a persistent Markdown wiki with typed knowledge graph, hybrid search, and contradiction detection. It supports 16+ agents and offline use.</description></item><item><title>WhyHow Knowledge Graph Studio: building RAG-native knowledge graphs with MongoDB and OpenAI</title><link>https://ramdi.fr/github-stars/whyhow-knowledge-graph-studio-building-rag-native-knowledge-graphs-with-mongodb-and-openai/</link><pubDate>Mon, 04 May 2026 10:23:01 +0000</pubDate><guid>https://ramdi.fr/github-stars/whyhow-knowledge-graph-studio-building-rag-native-knowledge-graphs-with-mongodb-and-openai/</guid><description>WhyHow Knowledge Graph Studio builds RAG-native knowledge graphs using MongoDB and OpenAI embeddings, offering flexible triple-based graph construction for AI workflows.</description></item><item><title>Inside llm_wiki: a desktop app for building persistent LLM-powered personal wikis</title><link>https://ramdi.fr/github-stars/inside-llm-wiki-a-desktop-app-for-building-persistent-llm-powered-personal-wikis/</link><pubDate>Mon, 04 May 2026 10:05:49 +0000</pubDate><guid>https://ramdi.fr/github-stars/inside-llm-wiki-a-desktop-app-for-building-persistent-llm-powered-personal-wikis/</guid><description>llm_wiki uses a two-step chain-of-thought pipeline to build a self-maintaining knowledge base. It combines Tauri, knowledge graphs, and Louvain clustering for a unique personal wiki experience.</description></item></channel></rss>